Search results for: stock price prediction

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 135

Authors: R. Bhattu Babajee, Marie Sandrine Estelle Benoit

Abstract:

The past decades have witnessed a considerable institutional shift towards Central Bank Independence across economies of the world. The motivation behind such a change is the acceptance that increased central bank autonomy has the power of alleviating inflation bias. Hence, studying whether Central Bank Independence acts as a significant factor behind the price stability in the African economies or whether this macroeconomic aim in these countries result from other economic, political or social factors is a pertinent issue. The main research objective of this paper is to assess the relationship between central bank autonomy and inflation in African economies where inflation has proved to be a serious problem. In this optic, we shall measure the degree of CBI in Africa by computing the turnover rates of central banks governors thereby studying whether decisions made by African central banks are affected by external forces. The purpose of this study is to investigate empirically the association between Central Bank Independence (CBI) and inflation for 10 African economies over a period of 17 years, from 1995 to 2012. The sample includes Botswana, Egypt, Ghana, Kenya, Madagascar, Mauritius, Mozambique, Nigeria, South Africa, and Uganda. In contrast to empirical research, we have not been using the usual static panel model for it is associated with potential mis specification arising from the absence of dynamics. To this issue a dynamic panel data model which integrates several control variables has been used. Firstly, the analysis includes dynamic terms to explain the tenacity of inflation. Given the confirmation of inflation inertia, that is very likely in African countries there exists the need for including lagged inflation in the empirical model. Secondly, due to known reverse causality between Central Bank Independence and inflation, the system generalized method of moments (GMM) is employed. With GMM estimators, the presence of unknown forms of heteroskedasticity is admissible as well as auto correlation in the error term. Thirdly, control variables have been used to enhance the efficiency of the model. The main finding of this paper is that central bank independence is negatively associated with inflation even after including control variables.

Keywords: central bank independence, inflation, macroeconomic variables, price stability

Procedia PDF Downloads 360

Authors: Soheila Sadeghi

Abstract:

Construction projects are complex and often subject to significant cost overruns due to the multifaceted nature of the activities involved. Accurate cost estimation is crucial for effective budget planning and resource allocation. Traditional methods for predicting overruns often rely on expert judgment or analysis of historical data, which can be time-consuming, subjective, and may fail to consider important factors. However, with the increasing availability of data from construction projects, machine learning techniques can be leveraged to improve the accuracy of overrun predictions. This study applied machine learning algorithms to enhance the prediction of cost overruns in a case study of a construction project. The methodology involved the development and evaluation of two machine learning models: Random Forest and Neural Networks. Random Forest can handle high-dimensional data, capture complex relationships, and provide feature importance estimates. Neural Networks, particularly Deep Neural Networks (DNNs), are capable of automatically learning and modeling complex, non-linear relationships between input features and the target variable. These models can adapt to new data, reduce human bias, and uncover hidden patterns in the dataset. The findings of this study demonstrate that both Random Forest and Neural Networks can significantly improve the accuracy of cost overrun predictions compared to traditional methods. The Random Forest model also identified key cost drivers and risk factors, such as changes in the scope of work and delays in material delivery, which can inform better project risk management. However, the study acknowledges several limitations. First, the findings are based on a single construction project, which may limit the generalizability of the results to other projects or contexts. Second, the dataset, although comprehensive, may not capture all relevant factors influencing cost overruns, such as external economic conditions or political factors. Third, the study focuses primarily on cost overruns, while schedule overruns are not explicitly addressed. Future research should explore the application of machine learning techniques to a broader range of projects, incorporate additional data sources, and investigate the prediction of both cost and schedule overruns simultaneously.

Keywords: cost prediction, machine learning, project management, random forest, neural networks

Procedia PDF Downloads 36

Authors: R. G. Ariyawansa, M. A. N. R. M. Perera

Abstract:

“House” is a powerful symbol of socio-economic background of individuals and families. In fact, housing provides all types of needs/wants from basic needs to self-actualization needs. This phenomenon can be realized only having analyzed hidden motives of buyers and sellers of the housing market. Hence, the aim of this study is to examine the socio-economic insight of the secondary housing market in Colombo suburbs. This broader aim was achieved via analyzing the general pattern of the secondary housing market, identifying socio-economic motives of sellers of the secondary housing market, and reviewing sellers’ experience of buyer behavior. A purposive sample of 50 sellers from popular residential areas in Colombo such as Maharagama, Kottawa, Piliyandala, Punnipitiya, and Nugegoda was used to collect primary data instead of relevant secondary data from published and unpublished reports. The sample was limited to selling price ranging from Rs15 million to Rs25 million, which apparently falls into middle and upper-middle income houses in the context. Participatory observation and semi-structured interviews were adopted as key data collection tools. Data were descriptively analyzed. This study found that the market is mainly handled by informal agents who are unqualified and unorganized. People such as taxi/tree-wheel drivers, boutique venders, security personals etc. are engaged in housing brokerage as a part time career. Few fulltime and formally organized agents were found but they were also not professionally qualified. As far as housing quality is concerned, it was observed that 90% of houses was poorly maintained and illegally modified. They are situated in poorly maintained neighborhoods as well. Among the observed houses, 2% was moderately maintained and 8% was well maintained and modified. Major socio-economic motives of sellers were “migrating foreign countries for education and employment” (80% and 10% respectively), “family problems” (4%), and “social status” (3%). Other motives were “health” and “environmental/neighborhood problems” (3%). This study further noted that the secondary middle income housing market in the area directly related with the migrants who motivated for education in foreign countries, mainly Australia, UK and USA. As per the literature, families motivated for education tend to migrate Colombo suburbs from remote areas of the country. They are seeking temporary accommodation in lower middle income housing. However, the secondary middle income housing market relates with the migration from Colombo to major global cities. Therefore, final transaction price of this market may depend on migration related dates such as university deadlines, visa and other agreements. Hence, it creates a buyers’ market lowering the selling price. Also it was revealed that the buyers tend to trust more on this market as far as the quality of construction of houses is concerned than brand new houses which are built for selling purpose.

Keywords: informal housing market, hidden motives of buyers and sellers, secondary housing market, socio-economic insight

Procedia PDF Downloads 162

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: retail stores, faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition

Procedia PDF Downloads 146

Authors: Zhaoan Wang

Abstract:

Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.

Keywords: automated supply chain, intelligent manufacturing, predictive maintenance machine learning, feature engineering, model interpretation

Procedia PDF Downloads 122

Authors: Milica Karadzic, Lidija Jevric, Sanja Podunavac-Kuzmanovic, Strahinja Kovacevic, Anamarija Mandic, Katarina Penov Gasi, Marija Sakac, Aleksandar Okljesa, Andrea Nikolic

Abstract:

The present paper deals with chromatographic lipophilicity prediction of newly synthesized steroid derivatives. The prediction was achieved using in silico generated molecular descriptors and quantitative structure-retention relationship (QSRR) methodology with the artificial neural networks (ANN) approach. Chromatographic lipophilicity of the investigated compounds was expressed as retention factor value logk. For QSRR modeling, a feedforward back-propagation ANN with gradient descent learning algorithm was applied. Using the novel sum of ranking differences (SRD) method generated ANN models were ranked. The aim was to distinguish the most consistent QSRR model that can be found, and similarity or dissimilarity between the models that could be noticed. In this study, SRD was performed with average values of retention factor value logk as reference values. An excellent correlation between experimentally observed retention factor value logk and values predicted by the ANN was obtained with a correlation coefficient higher than 0.9890. Statistical results show that the established ANN models can be applied for required purpose. This article is based upon work from COST Action (TD1305), supported by COST (European Cooperation in Science and Technology).

Keywords: artificial neural networks, liquid chromatography, molecular descriptors, steroids, sum of ranking differences

Procedia PDF Downloads 313

Authors: Orkide Donma, Mustafa M. Donma

Abstract:

Basal metabolic rate (BMR) is widely used and an accepted measure of energy expenditure. Its principal determinant is body mass. However, this parameter is also correlated with a variety of other factors. The objective of this study is to measure BMR and compare it with the values obtained from predictive equations in adults classified according to their body mass index (BMI) values. 276 adults were included into the scope of this study. Their age, height and weight values were recorded. Five groups were designed based on their BMI values. First group (n = 85) was composed of individuals with BMI values varying between 18.5 and 24.9 kg/m². Those with BMI values varying from 25.0 to 29.9 kg/m² constituted Group 2 (n = 90). Individuals with 30.0-34.9 kg/m², 35.0-39.9 kg/m², > 40.0 kg/m² were included in Group 3 (n = 53), 4 (n = 28) and 5 (n = 20), respectively. The most commonly used equations to be compared with the measured BMR values were selected. For this purpose, the values were calculated by the use of four equations to predict BMR values, by name, introduced by Food and Agriculture Organization (FAO)/World Health Organization (WHO)/United Nations University (UNU), Harris and Benedict, Owen and Mifflin. Descriptive statistics, ANOVA, post-Hoc Tukey and Pearson’s correlation tests were performed by a statistical program designed for Windows (SPSS, version 16.0). p values smaller than 0.05 were accepted as statistically significant. Mean ± SD of groups 1, 2, 3, 4 and 5 for measured BMR in kcal were 1440.3 ± 210.0, 1618.8 ± 268.6, 1741.1 ± 345.2, 1853.1 ± 351.2 and 2028.0 ± 412.1, respectively. Upon evaluation of the comparison of means among groups, differences were highly significant between Group 1 and each of the remaining four groups. The values were increasing from Group 2 to Group 5. However, differences between Group 2 and Group 3, Group 3 and Group 4, Group 4 and Group 5 were not statistically significant. These insignificances were lost in predictive equations proposed by Harris and Benedict, FAO/WHO/UNU and Owen. For Mifflin, the insignificance was limited only to Group 4 and Group 5. Upon evaluation of the correlations of measured BMR and the estimated values computed from prediction equations, the lowest correlations between measured BMR and estimated BMR values were observed among the individuals within normal BMI range. The highest correlations were detected in individuals with BMI values varying between 30.0 and 34.9 kg/m². Correlations between measured BMR values and BMR values calculated by FAO/WHO/UNU as well as Owen were the same and the highest. In all groups, the highest correlations were observed between BMR values calculated from Mifflin and Harris and Benedict equations using age as an additional parameter. In conclusion, the unique resemblance of the FAO/WHO/UNU and Owen equations were pointed out. However, mean values obtained from FAO/WHO/UNU were much closer to the measured BMR values. Besides, the highest correlations were found between BMR calculated from FAO/WHO/UNU and measured BMR. These findings suggested that FAO/WHO/UNU was the most reliable equation, which may be used in conditions when the measured BMR values are not available.

Keywords: adult, basal metabolic rate, fao/who/unu, obesity, prediction equations

Procedia PDF Downloads 126

Authors: Anne Y. Faxer, Ellen Olausson, Jens Hagman, Ana Magazinius, Jenny J. Stier, Tommy Fransson, Oscar Enerback

Abstract:

While electric vehicles (both battery electric vehicles and plug-in hybrids) have been on the market for around 6 years, they are still far from mainstream and the knowledge of them is still low among the public. This is likely one of the reasons that Sweden, having one of the highest penetrations of electric vehicles in Europe, still has a long way to go in reaching a fossil free vehicle fleet. Car dealerships are an important medium that connects consumers to vehicles, but somehow, their role in introducing electric vehicles has not yet been thoroughly studied. Research from other domains shows that salespeople can affect customer decisions in their choice of products. The aim of this study is to explore the role of car dealerships when it comes to promoting electric vehicles. The long-term goal is to understand how they could be a key in the effort of achieving a mass introduction of electric vehicles in Sweden. By emulating the customer’s experience, this study investigates the interaction between car salespeople and customers, particularly examining whether they present electric vehicles as viable options. Covert participatory observations were conducted for data collection from four different brands at in total twelve car dealers. The observers worked in pairs and played the role of a customer with needs that could be matched by an electric vehicle. The data was summarized in observation protocols and analyzed using thematic coding. The result shows that only one of twelve salespeople offered an electric vehicle as the first option. When environmental factors were brought up by the observers, the salespeople followed up with lower fuel consumption internal combustion engine vehicles rather than suggesting an electric vehicle. All salespeople possessed at least basic knowledge about electric vehicles but their interest of selling them were low in most cases. One of the reasons could be that the price of electric vehicles is usually higher. This could be inferred from the finding that salespeople tend to have a strong focus on price and economy in their dialogues with customers, regardless which type of car they were selling. In conclusion, the study suggests that car salespeople have the potential to help the market to achieve mass introduction of electric vehicles; however, their potential needs to be exploited further. To encourage salespeople to prioritize electric vehicles in the sales process, right incentives need to be in place.

Keywords: car dealerships, covert participatory observation, customer perspective , electric vehicle, market penetration

Procedia PDF Downloads 190

Authors: Sylvain Fauveaux, T. Nowicki

Abstract:

Lightning protection is nowadays applied worldwide since the advent of international standards. Lightning protection is widely justified by the casualties and damages involved. As a matter of fact, the lightning business is constantly growing as more and more sensible areas need to be protected. However, the worldwide demand of copper materiel is increasing as well, its price too. Furthermore, the most frequently used method of protection is consuming a lot of copper. The copper production is also consuming a large amount of natural and power resources, not to mention the ecologic balance.

Keywords: ESEAT, Lightning protection , natural resources management, NF C 17-102, sustainable development

Procedia PDF Downloads 155

Authors: Neveen AlQasas, Daniel Johnson

Abstract:

Membranes for water treatment are an established technology that attracts great attention due to its simplicity and cost effectiveness. However, membranes in operation suffer from the adverse effect of membrane fouling. Bio-fouling is a phenomenon that occurs at the water-membrane interface, and is a dynamic process that is initiated by the adsorption of dissolved organic material, including biomacromolecules, on the membrane surface. After initiation, attachment of microorganisms occurs, followed by biofilm growth. The biofilm blocks the pores of the membrane and consequently results in reducing the water flux. Moreover, the presence of a fouling layer can have a substantial impact on the membrane separation properties. Understanding the mechanism of the initiation phase of biofouling is a key point in eliminating the biofouling on membrane surfaces. The adhesion and attachment of different fouling materials is affected by the surface properties of the membrane materials. Therefore, surface properties of different polymeric materials had been studied in terms of their surface energies and Hansen solubility parameters (HSP). The difference between the combined HSP parameters (HSP distance) allows prediction of the affinity of two materials to each other. The possibilities of measuring the HSP of different polymer films via surface measurements, such as contact angle has been thoroughly investigated. Knowing the HSP of a membrane material and the HSP of a specific foulant, facilitate the estimation of the HSP distance between the two, and therefore the strength of attachment to the surface. Contact angle measurements using fourteen different solvents on five different polymeric films were carried out using the sessile drop method. Solvents were ranked as good or bad solvents using different ranking method and ranking was used to calculate the HSP of each polymeric film. Results clearly indicate the absence of a direct relation between contact angle values of each film and the HSP distance between each polymer film and the solvents used. Therefore, estimating HSP via contact angle alone is not sufficient. However, it was found if the surface tensions and viscosities of the used solvents are taken in to the account in the analysis of the contact angle values, a prediction of the HSP from contact angle measurements is possible. This was carried out via training of a neural network model. The trained neural network model has three inputs, contact angle value, surface tension and viscosity of solvent used. The model is able to predict the HSP distance between the used solvent and the tested polymer (material). The HSP distance prediction is further used to estimate the total and individual HSP parameters of each tested material. The results showed an accuracy of about 90% for all the five studied films

Keywords: surface characterization, hansen solubility parameter estimation, contact angle measurements, artificial neural network model, surface measurements

Procedia PDF Downloads 87

Authors: D. Mokatsanyane, J. Jansen Van Rensburg

Abstract:

This paper analyses the influence and impact of COVID-19 on major agricultural commodity prices in South Africa. According to a World Bank report, the agricultural sector in South Africa has been unable to reduce the domestic food crisis that has been occurring over the past years, hence the increased rate of poverty, which is currently at 55.5 percent as of April 2020. Despite the significance of this sector, empirical findings concluded that the agricultural sector now accounts for 1.88 percent of South Africa's gross domestic product (GDP). Suggesting that the agricultural sector's contribution to the economy has diminished. Despite the low contribution to GDP, this primary sector continues to play an essential role in the economy. Over the past years, multiple factors have contributed to the soaring commodities prices, namely, climate shocks, biofuel demand, demand and supply shocks, the exchange rate, speculation in commodity derivative markets, trade restrictions, and economic growth. The COVID-19 outbursts have currently disturbed the supply and demand of staple crops. To address the disruption, the government has exempted the agricultural sector from closure and restrictions on movement. The spread of COVID-19 has caused turmoil all around the world, but mostly in developing countries. According to Statistic South Africa, South Africa's economy decreased by seven percent in 2020. Consequently, this has arguably made the agricultural sector the most affected sector since slumped economic growth negatively impacts food security, trade, farm livelihood, and greenhouse gas emissions. South Africa is sensitive to the fruitfulness of global food chains. Restrictions in trade, reinforced sanitary control systems, and border controls have influenced food availability and prices internationally. The main objective of this study is to evaluate the behavior of agricultural commodity prices pre-and during-COVID to determine the impact of volatility drivers on these crops. Historical secondary data of spot prices for the top five major commodities, namely white maize, yellow maize, wheat, soybeans, and sunflower seeds, are analysed from 01 January 2017 to 1 September 2021. The timeframe was chosen to capture price fluctuations between pre-COVID-19 (01 January 2017 to 23 March 2020) and during-COVID-19 (24 March 2020 to 01 September 2021). The Generalised Autoregressive Conditional Heteroscedasticity (GARCH) statistical model will be used to measure the influence of price fluctuations. The results reveal that the commodity market has been experiencing volatility at different points. Extremely high volatility is represented during the first quarter of 2020. During this period, there was high uncertainty, and grain prices were very volatile. Despite the influence of COVID-19 on agricultural prices, the demand for these commodities is still existing and decent. During COVID-19, analysis indicates that prices were low and less volatile during the pandemic. The prices and returns of these commodities were low during COVID-19 because of the government's actions to respond to the virus's spread, which collapsed the market demand for food commodities.

Keywords: commodities market, commodity prices, generalised autoregressive conditional heteroscedasticity (GARCH), Price volatility, SAFEX

Procedia PDF Downloads 166

Authors: Thapa M., J.P. Dutta, K.R. Pandey, R.R. Kattel

Abstract:

Nepal is extremely vulnerable to the impact of climate change. To mitigate the climate change effects on agricultural production and productivity a range of adaptive strategies needs to be considered. The study was conducted to assess organic paddy production as a coping strategy to the adverse impact of climate change in Phulbari, VDC of Chitwan district. Altogether, 120 respondents (60 adopters of organic farming and 60 from non adopter) were selected using snowball technique of sampling. Pre- tested interview schedule, direct observation, focus group discussion, key informant interview as well as secondary data were used to collect the required information. Factors determining the adoption of organic farming were found to be age, year of schooling, training, frequency of extension contact, perception about climate change, economically active members and poor. A unit increase in these factors except poor would increase the probability of adoption by 4.1%, 7.5%, 7.8%, 43.1%, 41.8% and 7% respectively. However, for poor, it would decrease the probability of adoption of organic farming by 5.1%. Average organic matter content in the adopters' field was higher (2.7%) than the non-adopters' field (2.5%). The regression result showed that type of farmer, price and area under rice cultivation had positive and significant relationship with income; however dependency ratio had negative relationship. As the year of adoption of organic farming increases, the production of rice decline in the first two years then after goes on increasing but the cost of production goes on decreasing with the year of adoption. The respondents adapted to the changing climate through diversification of crops, use of resistance varieties and following good cropping pattern. Gradually growing consumers' awareness about health, preference towards quality food products are the strong points behind organic farming, whereas lacks of bio-fertilizers, lack of effective extension services, no price differentiation between organic and inorganic products were the weak points. There is need for more training and education to change the attitude of farmers and enhance their confidence about the role of organic farming to cope with climate change impact.

Keywords: Organic farming, climate change, sustainable development

Procedia PDF Downloads 450

Authors: Fatemeh Sadat Sharifi

Abstract:

In this research, a barotropic model was employed to consider the tidal studies in the Persian Gulf and Oman Sea, where the only sufficient force was the tidal force. To do that, a finite-difference, free-surface model called Regional Ocean Modeling System (ROMS), was employed on the data over the Persian Gulf and Oman Sea. To analyze flow patterns of the region, the results of limited size model of The Finite Volume Community Ocean Model (FVCOM) were appropriated. The two points were determined since both are one of the most critical water body in case of the economy, biology, fishery, Shipping, navigation, and petroleum extraction. The OSU Tidal Prediction Software (OTPS) tide and observation data validated the modeled result. Next, tidal elevation and speed, and tidal analysis were interpreted. Preliminary results determine a significant accuracy in the tidal height compared with observation and OTPS data, declaring that tidal currents are highest in Hormuz Strait and the narrow and shallow region between Iranian coasts and Islands. Furthermore, tidal analysis clarifies that the M_2 component has the most significant value. Finally, the Persian Gulf tidal currents are divided into two branches: the first branch converts from south to Qatar and via United Arab Emirate rotates to Hormuz Strait. The secondary branch, in north and west, extends up to the highest point in the Persian Gulf and in the head of Gulf turns counterclockwise.

Keywords: numerical model, barotropic tide, tidal currents, OSU tidal prediction software, OTPS

Procedia PDF Downloads 126

Authors: Karim Akkouche, Amine Nekmouche, Leyla Bouzid

Abstract:

This study focuses on the development of a multifunctional Expert System (ES) called post-seismic damage inspection tool (PSDIT), a powerful tool which allows the evaluation, the processing, and the archiving of the collected data stock after earthquakes. PSDIT can be operated by two user types; an ordinary user (ingineer, expert, or architect) for the damage visual inspection and an administrative user for updating the knowledge and / or for adding or removing the ordinary user. The knowledge acquisition is driven by a hierarchical knowledge model, the Information from investigation reports and those acquired through feedback from expert / engineer questionnaires are part.

Keywords: .disaster, damaged structures, damage assessment, expert system

Procedia PDF Downloads 77

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 100

Authors: Ru-Yin Yang, Chi Wu, Cheng-Yu Tsai, Yin-Tzu Lin, Wen-Te Liu

Abstract:

Background: Sleep breathing disorder (SDB) is a condition demonstrated by recurrent episodes of the airway obstruction leading to intermittent hypoxia and quality fragmentation during sleep time. However, the procedures for SDB severity examination remain complicated and costly. Objective: The objective of this study is to establish a simplified examination method for SDB by the respiratory impendence pattern sensor combining the signal processing and machine learning model. Methodologies: We records heart rate variability by the electrocardiogram and respiratory pattern by impendence. After the polysomnography (PSG) been done with the diagnosis of SDB by the apnea and hypopnea index (AHI), we calculate the episodes with the absence of flow and arousal index (AI) from device record. Subjects were divided into training and testing groups. Neuron network was used to establish a prediction model to classify the severity of the SDB by the AI, episodes, and body profiles. The performance was evaluated by classification in the testing group compared with PSG. Results: In this study, we enrolled 66 subjects (Male/Female: 37/29; Age:49.9±13.2) with the diagnosis of SDB in a sleep center in Taipei city, Taiwan, from 2015 to 2016. The accuracy from the confusion matrix on the test group by NN is 71.94 %. Conclusion: Based on the models, we established a prediction model for SDB by means of the wearable sensor. With more cases incoming and training, this system may be used to rapidly and automatically screen the risk of SDB in the future.

Keywords: sleep breathing disorder, apnea and hypopnea index, body parameters, neuron network

Procedia PDF Downloads 139

Authors: Rafayel K. Kostanyan

Abstract:

The opportunities of use of metallic magnesium as a generator of hydrogen gas, as well as thermal and electric energy is presented in the paper. Various schemes of magnesium application are discussed and power characteristics of corresponding devices are presented. Economic estimation of hydrogen price obtained by different methods is made, including the use of magnesium as a source of hydrogen for transportation in comparison with gasoline. Details and prospects of our new inexpensive technology of magnesium production from magnesium hydroxide and magnesium bearing rocks (which are available worldwide and in Armenia) are analyzed. It is estimated the threshold cost of Mg production at which application of this metal in power engineering is economically justified.

Keywords: energy, electrodialysis, magnesium, new technology

Procedia PDF Downloads 266

Authors: Sheikh Mohammed Rafiul Huque

Abstract:

Bangladesh since its inception has been an economy that is fuelled by agriculture and agriculture has significant contribution to the GDP of Bangladesh. The agriculture of Bangladesh predominantly and historically dependent on organic sources of raw material though the place has taken in decades by inorganic sources of raw materials due to the high demand of food for rapidly growing of population. Meanwhile, a new market segment, which is niche market, has been evolving in the urban area in favor of organic products, though 71.1% population living in rural areas is dependent mainly on conventional products. The new market segment is search of healthy and safer source of food and they could believe that organic products are the solution of that. In Bangladesh, food adulteration is very common practices among the shop-keepers to extend the shelf life of raw vegetables and fruits. The niche group of city dwellers is aware about the fact and gradually shifting their buying behavior to organic products. A recent survey on organic farming revealed that 16,200 hectares under organic farming in recent time, which was only 2,500 hectares in 2008. This study is focused on consumer awareness of organic products and tried to explore the factors affecting organic food consumption among high income group of people. The hypothesis is developed to explore the effect of gender (GENDER), ability to purchase (ABILITY) and health awareness (HEALTH) on purchase intention (INTENTION). A snowball sampling was administered among the high income group of people in Dhaka city among 150 respondents. In this sampling process the study could identify only those samples who has consume organic products. A Partial Least Square (PLS) method was used to analyze data using path analysis. It was revealed from the analysis that coefficient determination R2 is 0.829 for INTENTION endogenous latent variable. This means that three latent variables (GENDER, ABILITY, and HEALTH) significantly explain 82.9% of the variance in INTENTION of purchasing organic products. Moreover, GENDER solely explains 6.3% and 8.6% variability of ABILITY and HEALTH respectively. The inner model suggests that HEALTH has strongest negative effect on INTENTION (-0.647) followed by ABILITY (0.344) and GENDER (0.246). The hypothesized path relationship between ABILITY->INTENTION, HEALTH->INTENTION and GENDER->INTENTION are statistically significant. Furthermore, the hypothesized path relationship between GENDER->ABILITY (0.262) and GENDER->HEALTH (-0.292) also statistically significant. The purpose of the study is to demonstrate how an organic product producer can improve his participatory guarantee system (PGS) while marketing the products. The study focuses on understanding gender (GENDER), ability (ABILITY) and health (HEALTH) factors while positioning the products (INTENTION) in the mind of the consumer. In this study, the respondents are found to care about high price and ability to purchase variables with loading -0.920 and 0.898. They are good indicators of ability to purchase (ABILITY). The marketers should consider about price of organic comparing to conventional products while marketing, otherwise, that will create negative intention to buy with a loading of -0.939. Meanwhile, it is also revealed that believability of chemical free component in organic products and health awareness affects health (HEALTH) components with high loading -0.941 and 0.682. The study analyzes that low believability of chemical free component and high price of organic products affects intension to buy. The marketers should not overlook this point while targeting the consumers in Bangladesh.

Keywords: health awareness, organic products, purchase ability, purchase intention

Procedia PDF Downloads 370

Authors: Jameelah Omolara Yaqub

Abstract:

One of the main reasons for the existence of central bank is that it is believed that central banks have some influence on private sector decisions which will enable the Central Bank to achieve some of its objectives especially that of stable price and economic growth. By the assumption of the New Keynesian theory that prices are fully flexible in the short run, the central bank can temporarily influence real interest rate and, therefore, have an effect on real output in addition to nominal prices. There is, therefore, the need for the Central Bank to monitor, respond to, and influence private sector decisions appropriately. This thus shows that the Central Bank and the private sector will both affect and be affected by each other implying considerable interdependence between the sectors. The interdependence may be simultaneous or not depending on the level of information, readily available and how sensitive prices are to agents’ expectations about the future. The aim of this paper is, therefore, to determine whether the interdependence between asset prices and monetary policy are simultaneous or not and how important is this relationship. Studies on the effects of monetary policy have largely used VAR models to identify the interdependence but most have found small effects of interaction. Some earlier studies have ignored the possibility of simultaneous interdependence while those that have allowed for simultaneous interdependence used data from developed economies only. This study, therefore, extends the literature by using data from a developing economy where information might not be readily available to influence agents’ expectation. In this study, the direction of relationship among variables of interest will be tested by carrying out the Granger causality test. Thereafter, the interaction between asset prices and monetary policy in Nigeria will be tested. Asset prices will be represented by the NSE index as well as real estate prices while monetary policy will be represented by money supply and the MPR respectively. The VAR model will be used to analyse the relationship between the variables in order to take account of potential simultaneity of interdependence. The study will cover the period between 1980 and 2014 due to data availability. It is believed that the outcome of the research will guide monetary policymakers especially the CBN to effectively influence the private sector decisions and thereby achieve its objectives of price stability and economic growth.

Keywords: asset prices, granger causality, monetary policy rate, Nigeria

Procedia PDF Downloads 212

Authors: Jihee Jang, Seowon Yoon, Gaeun Son, Minjung Kang, Joon Yeon Choeh, Kee-Hong Choi

Abstract:

Background: Self-report multiple choice questionnaires have been widely utilized to quantitatively measure one’s personality and psychological constructs. Despite several strengths (e.g., brevity and utility), self-report multiple-choice questionnaires have considerable limitations in nature. With the rise of machine learning (ML) and Natural language processing (NLP), researchers in the field of psychology are widely adopting NLP to assess psychological constructs to predict human behaviors. However, there is a lack of connections between the work being performed in computer science and that psychology due to small data sets and unvalidated modeling practices. Aims: The current article introduces the study method and procedure of phase II, which includes the interview questions for the five-factor model (FFM) of personality developed in phase I. This study aims to develop the interview (semi-structured) and open-ended questions for the FFM-based personality assessments, specifically designed with experts in the field of clinical and personality psychology (phase 1), and to collect the personality-related text data using the interview questions and self-report measures on personality and psychological distress (phase 2). The purpose of the study includes examining the relationship between natural language data obtained from the interview questions, measuring the FFM personality constructs, and psychological distress to demonstrate the validity of the natural language-based personality prediction. Methods: The phase I (pilot) study was conducted on fifty-nine native Korean adults to acquire the personality-related text data from the interview (semi-structured) and open-ended questions based on the FFM of personality. The interview questions were revised and finalized with the feedback from the external expert committee, consisting of personality and clinical psychologists. Based on the established interview questions, a total of 425 Korean adults were recruited using a convenience sampling method via an online survey. The text data collected from interviews were analyzed using natural language processing. The results of the online survey, including demographic data, depression, anxiety, and personality inventories, were analyzed together in the model to predict individuals’ FFM of personality and the level of psychological distress (phase 2).

Keywords: personality prediction, psychological distress prediction, natural language processing, machine learning, the five-factor model of personality

Procedia PDF Downloads 76

Authors: Kyu Jin Kim, Byung Kwan Oh, Hyo Seon Park

Abstract:

The seismic responses-based structural health monitoring system has been performed to prevent seismic damage. Structural seismic damage of building is caused by the instantaneous stress concentration which is related with dynamic characteristic of earthquake. Meanwhile, seismic response analysis to estimate the dynamic responses of building demands significantly high computational cost. To prevent the failure of structural members from the characteristic of the earthquake and the significantly high computational cost for seismic response analysis, this paper presents an artificial neural network (ANN) based prediction model for dynamic responses of building considering specific time length. Through the measured dynamic responses, input and output node of the ANN are formed by the length of specific time, and adopted for the training. In the model, evolutionary radial basis function neural network (ERBFNN), that radial basis function network (RBFN) is integrated with evolutionary optimization algorithm to find variables in RBF, is implemented. The effectiveness of the proposed model is verified through an analytical study applying responses from dynamic analysis for multi-degree of freedom system to training data in ERBFNN.

Keywords: structural health monitoring, dynamic response, artificial neural network, radial basis function network, genetic algorithm

Procedia PDF Downloads 297

Authors: D. G. Badagha, C. D. Modhera, S. A. Vasanwala

Abstract:

There is a great challenge for civil engineering field to contribute in environment prevention by finding out alternatives of cement and natural aggregates. There is a problem of global warming due to cement utilization in concrete, so it is necessary to give sustainable solution to produce concrete containing waste. It is very difficult to produce designated grade of concrete containing different ingredient and water cement ratio including waste to achieve desired fresh and harden properties of concrete as per requirement and specifications. To achieve the desired grade of concrete, a number of trials have to be taken, and then after evaluating the different parameters at long time performance, the concrete can be finalized to use for different purposes. This research work is carried out to solve the problem of time, cost and serviceability in the field of construction. In this research work, artificial neural network introduced to fix proportion of concrete ingredient with 50% waste replacement for M20, M25, M30, M35, M40, M45, M50, M55 and M60 grades of concrete. By using the neural network, mix design of high performance concrete was finalized, and the main basic mechanical properties were predicted at 3 days, 7 days and 28 days. The predicted strength was compared with the actual experimental mix design and concrete cube strength after 3 days, 7 days and 28 days. This experimentally and neural network based mix design can be used practically in field to give cost effective, time saving, feasible and sustainable high performance concrete for different types of structures.

Keywords: artificial neural network, high performance concrete, rebound hammer, strength prediction

Procedia PDF Downloads 150

Authors: Moridi Fatemeh, Dasineh Mehdi, Jafari Narges

Abstract:

The aim of this study was to investigate the relationship between dividends and investment in a condition of cash flow uncertainty. Previous studies have also found some evidence that there is N-shaped relationship between dividends and investment given different levels of cash uncertainly. Thus, this study examines this relationship over the period 2009-2014 in Tehran Stock Exchange (TSE). Based on our sample and new variables, we found reverse N-shaped relationship in different levels of cash flow uncertainly. This shape was descending in cash flow certainly and uncertainly but it is ascending in medial position.

Keywords: dividends, investment, nonlinear relationship, uncertainty of cash flow

Procedia PDF Downloads 323

Authors: Vinícius L. L. Morrone, David Douek, Helder M. F. Pereira, Bernadete L. M. Grandolpho

Abstract:

This work aimed to identify the relationships between the level of consumer environmental awareness and their search for sustainable properties, as well as to understand the main sustainability structures considered by these consumers during the decision process. Additionally, the paper looked up to the influence environmental awareness and financial status have over the disposition of buyers to pay more for sustainable properties. To achieve these objectives, 318 questionnaires were answered electronically, after being sent to the Green Building Brazil email basis, as to other Real Estate developers client basis. From all the questionnaires answered, 71 were discarded, leaving a total amount of 247 admitted questionnaires to be analyzed. The responses were evaluated based on the theory of consumer decision making, especially on the influence factors of this process. The data were processed using a PLS model, using the R software. The results have shown that the level of consumer environmental awareness effectively affects the consumer’s will of acquiring a sustainable property or, at least, a property with some environmental friendly structures. The consumer’s environmental awareness also positively impacts the importance consumers give to individual environmental friendly structures. Also, as a consumer value to those individual structures raises, it is also observed a raise in his will to buy a sustainable property. Additionally, the impact of consumer’s environmental awareness and financial status over the willingness to pay more for a property with those attributes. The results indicate that there was no relationship between consumers' environmental awareness and their willingness to pay more for a sustainable property. On the other hand, the financial status and the family income of the consumers showed a positive relation with the willingness to pay more for a sustainable property. This indicates that consumers with better financial conditions, which according to the analysis do not necessarily have a greater environmental awareness, are those who are willing to pay more for a sustainable property. Thus, this study indicates that, even if the environmental awareness impact positively the demand for sustainable structures and properties, this impact is not price reflected, due to the price elasticity of the consumption, especially for a category of lower income consumers. This paper adds to the literature in the way it projects some guidelines to the consumer’s decision process in the Real Estate market in emerging economies, as well as it presents some drivers to pricing decisions.

Keywords: consumer behavior, environmental awareness, real estate pricing, sustainable buildings

Procedia PDF Downloads 183

Authors: Mohamed Sahli, David Bassir, Thierry Barriere, Xavier Roizard

Abstract:

Predicting the behaviour of the Ti-6Al-4V alloy during the turning operation was very important in the choice of suitable cutting tools and also in the machining strategies. In this study, a 3D model with thermo-mechanical coupling has been proposed to study the influence of cutting parameters and also lubrication on the performance of cutting tools. The constants of the constitutive Johnson-Cook model of Ti-6Al-4V alloy were identified using inverse analysis based on the parameters of the orthogonal cutting process. Then, numerical simulations of the finishing machining operation were developed and experimentally validated for the cylindrical stock removal stage with the finishing cutting tool.

Keywords: titanium turning, cutting tools, FE simulation, chip

Procedia PDF Downloads 169

Authors: Piotr Prewysz-Kwinto, Grazyna Voss

Abstract:

Accounting policies are a set of solutions compliant with legal regulations that an entity selects and adopts, and which guarantee a proper quality of financial statements. Those solutions may differ depending on whether the entity adopts national or international accounting standards. The aim of this article is to present accounting principles (policies) in Polish and international legal regulations and their adoption in selected Polish companies listed on the Warsaw Stock Exchange. The research method adopted in this work is the analysis and evaluation of legal conditions in Polish companies.

Keywords: accounting policies, international financial reporting standards, financial statement, method of measuring

Procedia PDF Downloads 374

Authors: Shashank Tiwari

Abstract:

The most common method of drug delivery is the oral solid dosage form, of which tablets and capsules are predominant. The tablet is more widely accepted and used compared to capsules for a number of reasons, such as cost/price, tamper resistance, ease of handling and packaging, ease of identification, and manufacturing efficiency. Over the past several years, the issue of tamper resistance has resulted in the conversion of most over-the-counter (OTC) drugs from capsules to predominantly all tablets.

Keywords: capsule, drug delivery, dosages, solid, tablet

Procedia PDF Downloads 430

Authors: Harish Krishnamurthy, Anna Lafontant, Ren Yi

Abstract:

Unidentified Flying Objects (UFOs) have been an interesting topic for most enthusiasts and hence people all over the United States report such findings online at the National UFO Report Center (NUFORC). Some of these reports are a hoax and among those that seem legitimate, our task is not to establish that these events confirm that they indeed are events related to flying objects from aliens in outer space. Rather, we intend to identify if the report was a hoax as was identified by the UFO database team with their existing curation criterion. However, the database provides a wealth of information that can be exploited to provide various analyses and insights such as social reporting, identifying real-time spatial events and much more. We perform analysis to localize these time-series geospatial events and correlate with known real-time events. This paper does not confirm any legitimacy of alien activity, but rather attempts to gather information from likely legitimate reports of UFOs by studying the online reports. These events happen in geospatial clusters and also are time-based. We look at cluster density and data visualization to search the space of various cluster realizations to decide best probable clusters that provide us information about the proximity of such activity. A random forest classifier is also presented that is used to identify true events and hoax events, using the best possible features available such as region, week, time-period and duration. Lastly, we show the performance of the scheme on various days and correlate with real-time events where one of the UFO reports strongly correlates to a missile test conducted in the United States.

Keywords: time-series clustering, feature extraction, hoax prediction, geospatial events

Procedia PDF Downloads 369

Authors: Mohammed N. Al Kindi, Mazin Al Khabouri, Khalsa Al Lamki, Tommasso Pappuci, Giovani Romeo, Nadia Al Wardy

Abstract:

Hereditary hearing loss is a heterogeneous group of complex disorders with an overall incidence of one in every five hundred newborns presented as syndromic and non-syndromic forms. Cadherin-related 23 (CDH23) is one of the listed deafness causative genes. CDH23 is found to be expressed in the stereocilia of hair cells and the retina photoreceptor cells. Defective CDH23 has been associated mostly with prelingual severe-to-profound sensorineural hearing loss (SNHL) in either syndromic (USH1D) or non-syndromic SNHL (DFNB12). An Omani family diagnosed clinically with severe-profound sensorineural hearing loss was genetically analysed by whole exome sequencing technique. A novel homozygous missense variant, c.A7451C (p.D2484A), in exon 53 of CDH23 was detected. One hundred and thirty control samples were analysed where all were negative for the detected variant. The variant was analysed in silico for pathogenicity verification using several mutation prediction software. The variant proved to be a pathogenic mutation and is reported for the first time in Oman and worldwide. It is concluded that in silico mutation prediction analysis might be used as a useful molecular diagnostics tool benefiting both genetic counseling and mutation verification. The aspartic acid 2484 alanine missense substitution might be the main disease-causing mutation that damages CDH23 function and could be used as a genetic hearing loss marker for this particular Omani family.

Keywords: Cdh23, d2484a, in silico, Oman

Procedia PDF Downloads 209